Maneesha Perera
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maneesha Perera has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Julian de Hoog
Department of Mechanical Engineering School of Electrical, Mechanical and Infrastructure Engineering The University of Melbourne Melbourne Australia
7 shared publications - Kasun Bandara
School of Computing and Information Systems Melbourne Centre for Data Science The University of Melbourne Melbourne Australia
7 shared publications - Saman Kumara Halgamuge
The University of Melbourne
7 shared publications - Damith Senanayake
Dept. of Mechanical Eng AI Optimization and Pattern Recognition Research Group University of Melbourne Australia
2 shared publications Hansani Weeratunge
2 shared publications- Rajith Vidanaarachchi
The University of Melbourne
2 shared publications
Latest Publications
- Open Access
- 9 May 2026
- Published by Elsevier in SSRN Electronic Journal
Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose a novel attention-enhanced convolutional long short-term memory network to forecast cloud movement using infrared satellite imagery and investigate how improvements in cloud movement prediction translate into improved short-term forecasting of distributed solar generation. We evaluate the impact of attention in cloud movement forecasting by comparing attention-based and non-attention-based approaches. In addition, we provide insights into differences in solar forecast performance under cloud conditions corresponding to high and low cloud altitudes inferred from infrared imagery. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
- 9 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDistributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose a novel attention-enhanced convolutional long short-term memory network to forecast cloud movement using infrared satellite imagery and investigate how improvements in cloud movement prediction translate into improved short-term forecasting of distributed solar generation. We evaluate the impact of attention in cloud movement forecasting by comparing attention-based and non-attention-based approaches. In addition, we provide insights into differences in solar forecast performance under cloud conditions corresponding to high and low cloud altitudes inferred from infrared imagery. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
- Open Access
- 14 February 2026
- Published by Elsevier in SSRN Electronic Journal
Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose a novel attention-enhanced convolutional long short-term memory network to forecast cloud movement using infrared satellite imagery and investigate how improvements in cloud movement prediction translate into improved short-term forecasting of distributed solar generation. We evaluate the impact of attention in cloud movement forecasting by comparing attention-based and non-attention-based approaches. In addition, we provide insights into differences in solar forecast performance under cloud conditions corresponding to high and low cloud altitudes inferred from infrared imagery. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
- 14 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDistributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose a novel attention-enhanced convolutional long short-term memory network to forecast cloud movement using infrared satellite imagery and investigate how improvements in cloud movement prediction translate into improved short-term forecasting of distributed solar generation. We evaluate the impact of attention in cloud movement forecasting by comparing attention-based and non-attention-based approaches. In addition, we provide insights into differences in solar forecast performance under cloud conditions corresponding to high and low cloud altitudes inferred from infrared imagery. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
- Open Access
- 18 June 2025
- Published by SAGE Publications in Big Data & Society
- Vol. 12 (2)
Indigenous peoples and artificial intelligence: A systematic review and future directions
This systematic literature review addresses the intersection of two rapidly evolving areas of knowledge and practice: Indigenous Knowledge Systems (IKS) and artificial intelligence (AI). There is growing scholarly recognition of the rich and diverse nature of IKS, which are unique intergenerational understandings of worldly relations from an Indigenous standpoint. There is now a vast literature on the promise and pitfalls of AI. However, there is a lack of systematic reviews showing how these two dynamic literatures are intersecting, and what the major themes are. AI has the potential to assist the promotion of IKS; however, there are also potential risks arising from AI for Indigenous peoples, such as the erosion of cultural knowledge, and data-grabbing that fails to respect the principles of Indigenous Data Sovereignty. These risks can exacerbate existing knowledge hierarchies and socio-economic inequalities. In this paper, we conducted a systematic review of articles published between 2012 and 2023 (January) on Indigenous peoples and AI. We shed light upon four unique overlapping categories into which existing literature can be classified and comprehensively discuss literature under each category. The first two categories discuss AI’s role in assisting the promotion of IKS and the third focuses on the pitfalls of using AI for Indigenous peoples. The final category discusses how IKS itself can enrich the development of AI. We further identify several gaps in the literature and highlight avenues requiring attention on AI’s role with Indigenous peoples and their knowledge systems.
- 18 June 2025
- Published by SAGE Publications in Big Data & Society
- Vol. 12 (2)
Open AccessIndigenous peoples and artificial intelligence: A systematic review and future directions
This systematic literature review addresses the intersection of two rapidly evolving areas of knowledge and practice: Indigenous Knowledge Systems (IKS) and artificial intelligence (AI). There is growing scholarly recognition of the rich and diverse nature of IKS, which are unique intergenerational understandings of worldly relations from an Indigenous standpoint. There is now a vast literature on the promise and pitfalls of AI. However, there is a lack of systematic reviews showing how these two dynamic literatures are intersecting, and what the major themes are. AI has the potential to assist the promotion of IKS; however, there are also potential risks arising from AI for Indigenous peoples, such as the erosion of cultural knowledge, and data-grabbing that fails to respect the principles of Indigenous Data Sovereignty. These risks can exacerbate existing knowledge hierarchies and socio-economic inequalities. In this paper, we conducted a systematic review of articles published between 2012 and 2023 (January) on Indigenous peoples and AI. We shed light upon four unique overlapping categories into which existing literature can be classified and comprehensively discuss literature under each category. The first two categories discuss AI’s role in assisting the promotion of IKS and the third focuses on the pitfalls of using AI for Indigenous peoples. The final category discusses how IKS itself can enrich the development of AI. We further identify several gaps in the literature and highlight avenues requiring attention on AI’s role with Indigenous peoples and their knowledge systems.
- Open Access
Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning
Adapting Large Language Models (LLMs) that are extensively trained on abundant text data, and customizing the input prompt to enable time series forecasting has received considerable attention. While recent work has shown great potential for adapting the learned prior of LLMs, the formulation of the prompt to finetune LLMs remains challenging as prompt should be aligned with time series data. Additionally, current approaches do not effectively leverage word token embeddings which embody the rich representation space learned by LLMs. This emphasizes the need for a robust approach to formulate the prompt which utilizes the word token embeddings while effectively representing the characteristics of the time series. To address these challenges, we propose NNCL-TLLM: Nearest Neighbor Contrastive Learning for Time series forecasting via LLMs. First, we generate time series compatible text prototypes such that each text prototype represents both word token embeddings in its neighborhood and time series characteristics via end-to-end finetuning. Next, we draw inspiration from Nearest Neighbor Contrastive Learning to formulate the prompt while obtaining the top-$k$ nearest neighbor time series compatible text prototypes. We then fine-tune the layer normalization and positional embeddings of the LLM, keeping the other layers intact, reducing the trainable parameters and decreasing the computational cost. Our comprehensive experiments demonstrate that NNCL-TLLM outperforms in few-shot forecasting while achieving competitive or superior performance over the state-of-the-art methods in long-term and short-term forecasting tasks.
Open AccessRethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning
Adapting Large Language Models (LLMs) that are extensively trained on abundant text data, and customizing the input prompt to enable time series forecasting has received considerable attention. While recent work has shown great potential for adapting the learned prior of LLMs, the formulation of the prompt to finetune LLMs remains challenging as prompt should be aligned with time series data. Additionally, current approaches do not effectively leverage word token embeddings which embody the rich representation space learned by LLMs. This emphasizes the need for a robust approach to formulate the prompt which utilizes the word token embeddings while effectively representing the characteristics of the time series. To address these challenges, we propose NNCL-TLLM: Nearest Neighbor Contrastive Learning for Time series forecasting via LLMs. First, we generate time series compatible text prototypes such that each text prototype represents both word token embeddings in its neighborhood and time series characteristics via end-to-end finetuning. Next, we draw inspiration from Nearest Neighbor Contrastive Learning to formulate the prompt while obtaining the top-$k$ nearest neighbor time series compatible text prototypes. We then fine-tune the layer normalization and positional embeddings of the LLM, keeping the other layers intact, reducing the trainable parameters and decreasing the computational cost. Our comprehensive experiments demonstrate that NNCL-TLLM outperforms in few-shot forecasting while achieving competitive or superior performance over the state-of-the-art methods in long-term and short-term forecasting tasks.
- Open Access
Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with "attention" that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose an attention-based convolutional long short-term memory network to forecast cloud movement and apply an existing self-attention-based method previously proposed for video prediction to forecast cloud movement. We investigate and discuss the impact of cloud forecasts from attention-based methods towards forecasting distributed solar generation, compared to cloud forecasts from non-attention-based methods. We further provide insights into the different solar forecast performances that can be achieved for high and low altitude clouds. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
Open AccessDistributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with "attention" that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose an attention-based convolutional long short-term memory network to forecast cloud movement and apply an existing self-attention-based method previously proposed for video prediction to forecast cloud movement. We investigate and discuss the impact of cloud forecasts from attention-based methods towards forecasting distributed solar generation, compared to cloud forecasts from non-attention-based methods. We further provide insights into the different solar forecast performances that can be achieved for high and low altitude clouds. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
- 2 October 2024
- Published by Springer Nature in Digital Society
- Vol. 3 (3) , 1-37
Insights into Artificial Intelligence Bias: Implications for Agriculture
- 2 October 2024
- Published by Springer Nature in Digital Society
- Vol. 3 (3) , 1-37
Insights into Artificial Intelligence Bias: Implications for Agriculture
- Top Cited PapersOpen Access
- 6 March 2024
- Published by Elsevier in Applied Energy
- Vol. 361
Day-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data
- 6 March 2024
- Published by Elsevier in Applied Energy
- Vol. 361
Top Cited PapersOpen AccessDay-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data
- Open Access
Day-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data
Regional solar power forecasting, which involves predicting the total power generation from all rooftop photovoltaic systems in a region holds significant importance for various stakeholders in the energy sector. However, the vast amount of solar power generation and weather time series from geographically dispersed locations that need to be considered in the forecasting process makes accurate regional forecasting challenging. Therefore, previous work has limited the focus to either forecasting a single time series (i.e., aggregated time series) which is the addition of all solar generation time series in a region, disregarding the location-specific weather effects or forecasting solar generation time series of each PV site (i.e., individual time series) independently using location-specific weather data, resulting in a large number of forecasting models. In this work, we propose two deep-learning-based regional forecasting methods that can effectively leverage both types of time series (aggregated and individual) with weather data in a region. We propose two hierarchical temporal convolutional neural network architectures (HTCNN) and two strategies to adapt HTCNNs for regional solar power forecasting. At first, we explore generating a regional forecast using a single HTCNN. Next, we divide the region into multiple sub-regions based on weather information and train separate HTCNNs for each sub-region; the forecasts of each sub-region are then added to generate a regional forecast. The proposed work is evaluated using a large dataset collected over a year from 101 locations across Western Australia to provide a day ahead forecast. We compare our approaches with well-known alternative methods and show that the sub-region HTCNN requires fewer individual networks and achieves a forecast skill score of 40.2% reducing a statistically significant error by 6.5% compared to the best counterpart.
Open AccessDay-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data
Regional solar power forecasting, which involves predicting the total power generation from all rooftop photovoltaic systems in a region holds significant importance for various stakeholders in the energy sector. However, the vast amount of solar power generation and weather time series from geographically dispersed locations that need to be considered in the forecasting process makes accurate regional forecasting challenging. Therefore, previous work has limited the focus to either forecasting a single time series (i.e., aggregated time series) which is the addition of all solar generation time series in a region, disregarding the location-specific weather effects or forecasting solar generation time series of each PV site (i.e., individual time series) independently using location-specific weather data, resulting in a large number of forecasting models. In this work, we propose two deep-learning-based regional forecasting methods that can effectively leverage both types of time series (aggregated and individual) with weather data in a region. We propose two hierarchical temporal convolutional neural network architectures (HTCNN) and two strategies to adapt HTCNNs for regional solar power forecasting. At first, we explore generating a regional forecast using a single HTCNN. Next, we divide the region into multiple sub-regions based on weather information and train separate HTCNNs for each sub-region; the forecasts of each sub-region are then added to generate a regional forecast. The proposed work is evaluated using a large dataset collected over a year from 101 locations across Western Australia to provide a day ahead forecast. We compare our approaches with well-known alternative methods and show that the sub-region HTCNN requires fewer individual networks and achieves a forecast skill score of 40.2% reducing a statistically significant error by 6.5% compared to the best counterpart.
- Open Access
- 18 October 2023
- Published by Springer Nature in BMC Public Health
- Vol. 23 (1) , 1-10
FEEDBACK trial - A randomised control trial to investigate the effect of personalised feedback and financial incentives on reducing the incidence of road crashes
Background: Road crashes continue to pose a significant threat to global health. Young drivers aged between 18 and 25 are over-represented in road injury and fatality statistics, especially the first six months after obtaining their license. This study is the first multi-centre two-arm parallel-group individually randomised controlled trial (the FEEDBACK Trial) that will examine whether the delivery of personalised driver feedback plus financial incentives is superior to no feedback and no financial incentives in reducing motor vehicle crashes among young drivers (18 to 20 years) during the first year of provisional licensing. Methods: A total of 3,610 young drivers on their provisional licence (P1, the first-year provisional licensing) will participate in the trial over 28 weeks, including a 4-week baseline, 20-week intervention and 4-week post-intervention period. The primary outcome of the study will be police-reported crashes over the 20-week intervention period and the 4-week post-intervention period. Secondary outcomes include driving behaviours such as speeding and harsh braking that contribute to road crashes, which will be attained weekly from mobile telematics delivered to a smartphone app. Discussion: Assuming a positive finding associated with personalised driver feedback and financial incentives in reducing road crashes among young drivers, the study will provide important evidence to support policymakers in introducing the intervention(s) as a key strategy to mitigate the risks associated with the burden of road injury among this vulnerable population. Trial registration: Registered under the Australian New Zealand Clinical Trials Registry (ANZCTR) - ACTRN12623000387628p on April 17, 2023.
- 18 October 2023
- Published by Springer Nature in BMC Public Health
- Vol. 23 (1) , 1-10
Open AccessFEEDBACK trial - A randomised control trial to investigate the effect of personalised feedback and financial incentives on reducing the incidence of road crashes
Background: Road crashes continue to pose a significant threat to global health. Young drivers aged between 18 and 25 are over-represented in road injury and fatality statistics, especially the first six months after obtaining their license. This study is the first multi-centre two-arm parallel-group individually randomised controlled trial (the FEEDBACK Trial) that will examine whether the delivery of personalised driver feedback plus financial incentives is superior to no feedback and no financial incentives in reducing motor vehicle crashes among young drivers (18 to 20 years) during the first year of provisional licensing. Methods: A total of 3,610 young drivers on their provisional licence (P1, the first-year provisional licensing) will participate in the trial over 28 weeks, including a 4-week baseline, 20-week intervention and 4-week post-intervention period. The primary outcome of the study will be police-reported crashes over the 20-week intervention period and the 4-week post-intervention period. Secondary outcomes include driving behaviours such as speeding and harsh braking that contribute to road crashes, which will be attained weekly from mobile telematics delivered to a smartphone app. Discussion: Assuming a positive finding associated with personalised driver feedback and financial incentives in reducing road crashes among young drivers, the study will provide important evidence to support policymakers in introducing the intervention(s) as a key strategy to mitigate the risks associated with the burden of road injury among this vulnerable population. Trial registration: Registered under the Australian New Zealand Clinical Trials Registry (ANZCTR) - ACTRN12623000387628p on April 17, 2023.